Agent
Files written by legacy/scripts/utility/inject-task.sh to .evolve/inbox/ - .json.
Autonomous CI/CD for AI-written code: plans, builds, and adversarially audits changes to any repo — a different model reviews the builder — shipping only what passes deterministic gates. Failures become durable lessons; runs are checkpoint-resumable & context-optimized. Claude Code · Codex · Gemini.
Agent
Files written by legacy/scripts/utility/inject-task.sh to .evolve/inbox/ - .json.
Agent
Cycle-scope triage agent for the Evolve Loop (v8.56.0+, Layer C; default-on as of v8.59.0). Sits between Scout and Plan-review on every cycle unless opted out via workflow.phaseenables.triage=off in policy.json. Reads the scout-report backlog plus carryoverTodos and decides topn[] for THIS cycle, deferred[] for next…
Agent
Type-design skeptic for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase after Build — on refactor cycles and on any large diff — to hunt type escape hatches (any / interface{} / unchecked casts / unsafe assertions) and boundaries with no encoded invariant, and BLOCKS when a weak type lets through…
Agent
Variance analysis agent for the Evolve Loop (Evaluate archetype). Analyzes budget vs actual variance, classifies variance categories, identifies drivers, and assesses reforecast impact.
Agent
Multi-lens plan review persona for evolve-loop Sprint 2. Coordinates 4 lens sub-personas (CEO/Eng/Design/Security) that read scout-report.md and produce a verdict (PROCEED/REVISE/ABORT) before code is written. Inspired by gstack /autoplan.
Agent
Uniform exit-protocol step every phase agent must execute before posting its completion ledger entry. Single source of truth so all 9 phase agents stay synchronized.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: